Hybrid search, graph indexing, and vector-symbolic memory for AI agents
Stage
Not given
Startup
Founded
2023
2026
Based in
US
US
Pricing model
Freemium
Open source
Pricing
Free plan: 10,000 credits per month. Flex plan: $125/month with 50,000 credits included, then $25 per 10,000 credits. Flex Plus: $375/month with 200,000 credits included, then $75 per 40,000 credits. Enterprise: custom credits with negotiated rates. Credits consumed based on Episode size: 1 credit p
Open source under Apache-2.0 license. WARM Cloud is in development with usage-based pricing for sync, backup and verification; details to be published at launch.
Key features
Sub-200ms context retrieval at scale
Temporal context graphs with point-in-time queries
Hybrid search combining BM25 lexical and vector scoring
Vertex graph vector index with 2.29-2.75x throughput vs hnswlib
Vector-symbolic fact memory with holographic reduced representations
AES-256-GCM encryption at rest with Argon2id key derivation
Signed audit log with Ed25519 and W3C DID identity
Secure purge that overwrites deleted data with zeros
Crash-safe append-only log with checksumming
Native Rust API with Python HTTP client and Node.js bindings
MCP server integration for editors and AI agents
WARM Cloud sync, backup and verification without server access to keys or documents
What makes it different
Reduces token use by up to 90% compared to traditional retrieval
Temporal context graphs that track how business information changes over time
Enterprise-scale Context Lake supporting millions of graphs
Runs entirely locally in your process with no network calls or telemetry
Encryption at rest built into the open-source engine itself, not an enterprise add-on
Significantly faster vector search than hnswlib with graph-indexed vertex retrieval
Signed provenance and verified audit trail using C2PA, COSE and SCITT standards
Embedded library model eliminates dependency on external services or vendor lock-in
Zep
warm-rust